Skip to main content
Glama

news

by media.probable

Score a headline against Probable's observed base rates

score_headline
Read-onlyIdempotent

Classify one supplied headline and inspect coverage recurrence. Optional referenceContext adds explicit country, magnitude, industry or aviation scope. When sufficiently scoped, occurrenceReference separately supplies primary-source counts, exposure or published population rates with units and source periods. Missing fields, conflicts and hypothetical/disputed/historical wording are disclosed; news mentions never update source rates. Do not verify a headline, compare incompatible units, predict an outcome, or score a URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYes
referenceContextNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / referenceContext
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "aviationScope": {
+      "const": "us_scheduled_part121",
+      "type": "string"
+    },
+    "countryCode": {
+      "pattern": "^[A-Z]{3}$",
+      "type": "string"
+    },
+    "industry": {
+      "enum": [
+        "51",
+        "00",
+        "31-33",
+        "44-45"
+      ],
+      "type": "string"
+    },
+    "magnitude": {
+      "maximum": 10,
+      "minimum": 0,
+      "type": "number"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states that missing fields, conflicts, and hypothetical/disputed/historical wording are disclosed, and that 'news mentions never update source rates' — a key state-behavior guarantee. This goes well beyond the readOnly/idempotent annotations and tells the agent what side effects (or lack thereof) to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences are front-loaded with purpose, then scope, behavior, and prohibitions. Nothing is redundant with the title or schema, and every clause adds decision-relevant detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers inputs, scoping, output hints (occurrenceReference with counts/rates/units), and edge-case handling, which is substantial for a tool with no output schema. The only minor gap is that 'occurrenceReference' is mentioned without explicitly labeling it as part of the response, which could momentarily confuse an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With zero schema description coverage, the description compensates by explaining that title is the headline and referenceContext adds explicit country, magnitude, industry, or aviation scope. It doesn't spell out the enum codes or numeric limits, but it gives the semantic purpose of each parameter rather than just echoing the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence names a specific operation ('Classify one supplied headline and inspect coverage recurrence') on a specific resource, and the title anchors it to Probable's observed base rates. This clearly separates it from the sibling watch/edition/event tools, none of which perform headline scoring.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It sets clear scope: one supplied headline, optional referenceContext for scope, and explicit prohibitions ('Do not verify a headline, compare incompatible units, predict an outcome, or score a URL'). It does not name alternative tools, but given the sibling set this is not necessary; the when-not guidance is concrete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All news toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation3/5

The watch and edition tools are clearly distinct, but get_context and score_headline overlap heavily—both accept a headline, share the referenceContext parameter, and disclose withheld/conflicting info—and get_brief vs read_latest_edition both serve 'what's the latest news' requests. The verbose 'do not use for' guardrails in the descriptions help, but they also signal that the boundaries are not naturally obvious.

Naming Consistency4/5

All names follow snake_case verb_noun, with predictable patterns: list_* for collections, create/update/acknowledge for watch mutations, read_* for editions. Minor inconsistency exists between get_brief and read_latest_edition (both fetch news content) and between get_membership and list_watches (both return list-like info), but the overall scheme is readable and consistent.

Tool Count4/5

14 tools sits within the typical well-scoped band, and each tool appears to serve a real product feature. The surface is slightly broad for a 'news' server, spanning saved-watch management, edition reading/export, headline analysis, and membership/checkout, which makes it heavier than a focused news reader.

Completeness3/5

Edition access (list/read/export) and the analysis workflow (score/context/discover) are well covered, but the watch lifecycle has no delete_watch, leaving agents unable to remove saved watches—a real dead end. There is also no story-level read or search tool, though the descriptions explicitly scope that out.

Resources